Rajat Rawat
@rajat_s_rawat
34 Following 17 Followers
Did a model secretly train on another model's outputs?
Providers can catch this from server-side logs — Anthropic recently reported catching 29M such exchanges. But those methods need usage logs and infrastructure access; they don't work from the model itself.
Our paper does: compare a model to an earlier checkpoint of itself, and ask which candidate teacher best explains the shift between them. The true teacher stands out. 🧵
Show more
